Refactor code structure for improved readability and maintainability

workers/audio-denoise/Dockerfile

@@ -0,0 +1,23 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# ffmpeg (with arnndn/afftdn filters) + curl for model download
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends ffmpeg ca-certificates curl && \
+    rm -rf /var/lib/apt/lists/*
+
+# Download a standard RNNoise model for ffmpeg's arnndn filter.
+# Source: GregorR/rnnoise-models (beguiling-drafts, a widely used general model).
+# Non-fatal: if the download fails, handler.py falls back to afftdn.
+RUN mkdir -p /app/models && \
+    ( curl -fsSL -o /app/models/rnnoise.rnnn \
+        https://raw.githubusercontent.com/GregorR/rnnoise-models/master/beguiling-drafts-2018-08-30/bd.rnnn \
+      || echo "WARNING: RNNoise model download failed; will fall back to afftdn" )
+
+COPY workers/audio-denoise/requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY workers/audio-denoise/handler.py .
+
+CMD ["python3", "-u", "handler.py"]

workers/audio-denoise/README.md

@@ -0,0 +1,26 @@
+# Audio Denoise Worker (RNNoise / arnndn)
+
+RunPod Serverless CPU worker that removes background noise from audio using
+ffmpeg's RNNoise filter (`arnndn`), with a built-in FFT denoiser (`afftdn`)
+as an automatic fallback.
+
+## Contract
+- Input: `{"audio": "<base64>"}` — any format/sample rate. A `data:...;base64,`
+  prefix is stripped automatically.
+- Output: `{"audio": "<base64 WAV>"}` — denoised, 48 kHz mono WAV.
+- Error: `{"error": "<message>"}`.
+
+## Pipeline
+decode base64 -> temp input file -> `ffmpeg -i in -af arnndn=m=/app/models/rnnoise.rnnn -ar 48000 -ac 1 out.wav` -> read -> base64.
+
+## Deploy
+- Dockerfile path: `/workers/audio-denoise/Dockerfile`
+- Build context: repo root (`docker build -f workers/audio-denoise/Dockerfile .`)
+- GPU: none (CPU-only worker)
+- App env var to set: `RUNPOD_AUDIO_DENOISE_URL` (your deployed endpoint URL)
+
+## Model
+The Dockerfile downloads the `beguiling-drafts` RNNoise model from
+`GregorR/rnnoise-models` to `/app/models/rnnoise.rnnn`. If that download
+fails at build time, the handler transparently falls back to ffmpeg's
+built-in `afftdn` FFT denoiser (no model file needed).

workers/audio-denoise/handler.py

@@ -0,0 +1,70 @@
+_V = "/runpod-volume"
+import os
+if os.path.isdir(_V):
+    os.environ.setdefault("HF_HOME", os.path.join(_V, "huggingface"))
+
+import base64
+import subprocess
+import tempfile
+
+import runpod
+
+# Path where the Dockerfile places the RNNoise model file.
+RNNN_MODEL = "/app/models/rnnoise.rnnn"
+
+
+def _decode_b64(s):
+    if isinstance(s, str) and "," in s and s.strip().lower().startswith("data:"):
+        s = s.split(",", 1)[1]
+    return base64.b64decode(s)
+
+
+def _denoise(in_path, out_path):
+    """Run ffmpeg. Prefer RNNoise (arnndn) when a model file is present,
+    otherwise fall back to the built-in FFT denoiser (afftdn)."""
+    if os.path.isfile(RNNN_MODEL):
+        af = "arnndn=m=" + RNNN_MODEL
+    else:
+        af = "afftdn=nf=-25"
+
+    cmd = [
+        "ffmpeg", "-y", "-hide_banner", "-nostdin",
+        "-i", in_path,
+        "-af", af,
+        "-ar", "48000", "-ac", "1",
+        "-f", "wav",
+        out_path,
+    ]
+    proc = subprocess.run(cmd, capture_output=True)
+    if proc.returncode != 0:
+        raise RuntimeError(
+            "ffmpeg failed: " + proc.stderr.decode("utf-8", "replace")[-800:]
+        )
+
+
+def handler(event):
+    try:
+        inp = (event or {}).get("input") or {}
+        audio_b64 = inp.get("audio")
+        if not audio_b64:
+            return {"error": "Missing 'audio' in input"}
+
+        raw = _decode_b64(audio_b64)
+
+        with tempfile.TemporaryDirectory() as td:
+            in_path = os.path.join(td, "in")
+            out_path = os.path.join(td, "out.wav")
+            with open(in_path, "wb") as f:
+                f.write(raw)
+
+            _denoise(in_path, out_path)
+
+            with open(out_path, "rb") as f:
+                out_bytes = f.read()
+
+        return {"audio": base64.b64encode(out_bytes).decode("ascii")}
+    except Exception as exc:
+        return {"error": f"{type(exc).__name__}: {exc}"}
+
+
+runpod.serverless.start({"handler": handler})

workers/audio-denoise/requirements.txt

@@ -0,0 +1 @@
+runpod==1.7.9